fix(skills): use real --output-format flag in messaging-agents

src/skills/builtin/messaging-agents/SKILL.md

@@ -102,7 +102,7 @@ letta -p --from-agent $LETTA_AGENT_ID \
   "What do you know about the authentication system?"
 ```
 
-**Response (JSON format with `--output json`):**
+**Response (JSON format with `--output-format json`):**
 ```json
 {
   "type": "result",
@@ -170,7 +170,7 @@ letta -p --from-agent $LETTA_AGENT_ID \
 - Text-mode scripts return only the **final assistant message** (not tool calls, reasoning, or metadata)
 - JSON and stream-json responses include `agent_id`, `conversation_id`, and `environment.source` so you can continue the same conversation/runtime. Environment-routed turns also include `environment.id`, `connection_id`, `device_id`, and `name`.
 - The target agent may use tools, think, and reason - but you only see their final response
-- To see the full conversation transcript (including tool calls), use `letta messages list --agent <id>` targeting the other agent
+- To see the full conversation transcript (including tool calls), use `letta messages transcript --conversation <id>` (or `letta messages list --agent <id>`) targeting the other agent
 
 ## How It Works
 

src/skills/messaging-agents.test.ts

@@ -0,0 +1,41 @@
+import { describe, expect, test } from "bun:test";
+import { readFileSync } from "node:fs";
+import { join } from "node:path";
+import { CLI_FLAG_CATALOG } from "@/cli/args";
+
+const skill = readFileSync(
+  join(
+    process.cwd(),
+    "src",
+    "skills",
+    "builtin",
+    "messaging-agents",
+    "SKILL.md",
+  ),
+  "utf8",
+);
+
+// Headless flags the skill documents for `letta -p` messaging. Subcommand
+// flags (agents/messages/computers) are parsed by their own subcommand
+// parsers and are not part of the main CLI flag catalog.
+const HEADLESS_FLAGS_DOCUMENTED = [
+  "from-agent",
+  "agent",
+  "conversation",
+  "computer",
+  "output-format",
+] as const;
+
+describe("messaging-agents skill", () => {
+  test("documents headless flags the CLI parser accepts", () => {
+    for (const flag of HEADLESS_FLAGS_DOCUMENTED) {
+      expect(flag in CLI_FLAG_CATALOG).toBe(true);
+      expect(skill).toContain(`--${flag}`);
+    }
+  });
+
+  test("uses the real headless JSON output flag", () => {
+    expect(skill).toContain("--output-format json");
+    expect(skill).not.toContain("--output json");
+  });
+});